# Deconfounded Image Captioning: A Causal Retrospect Source: [Deconfounded Image Captioning: A Causal Retrospect]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:28:17.403Z Authors: Xu Yang, Hanwang Zhang, Jianfei Cai Published: 2020-03-09T04:59:05.000Z ## Abstract Dataset bias in vision-language tasks is becoming one of the main problems which hinders the progress of our community. Existing solutions lack a principled analysis about why modern image captioners easily collapse into dataset bias. In this paper, we present a novel perspective: Deconfounded Image Captioning (DIC), to find out the answer of this question, then retrospect modern neural image captioners, and finally propose a DIC framework: DICv1.0 to alleviate the negative effects brought by dataset bias. DIC is based on causal inference, whose two principles: the backdoor and front-door adjustments, help us review previous studies and design new effective models. In particular, we showcase that DICv1.0 can strengthen two prevailing captioning models and can achieve a single-model 131.1 CIDEr-D and 128.4 c40 CIDEr-D on Karpathy split and online split of the challenging MS COCO dataset, respectively. Interestingly, DICv1.0 is a natural derivation from our causal retrospect, which opens promising directions for image captioning. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Captioning on MS COCO Karpathy (test)](): Image Captioning; MS COCO Karpathy (test); CIDEr: 1.282. ## Original sources and implementation [Original paper]() [PDF]()